© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 25-TRANSCODER-HP
    7. 107206
    Prev
    Next
    INDEX
    Explanations

    our

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_25.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.25.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    æĺ¯æĪij们
    -0.33
    æĪij们éĥ½
    -0.32
    æĪij们å¿ħé¡»
    -0.32
    æĪijä»¬ä¹Ł
    -0.30
    è¿Ļæĺ¯æĪij们
    -0.30
    æĪij们
    -0.30
    æīĢ以æĪij们
    -0.29
     we
    -0.28
    æĪij们认为
    -0.28
    we
    -0.26
    POSITIVE LOGITS
    reas
    0.28
     indef
    0.27
    anguages
    0.27
    ENTS
    0.25
    utures
    0.25
    çĽİ
    0.24
    ände
    0.24
    çļĦæĥħ
    0.24
    ije
    0.24
    igate
    0.24
    Activations Density 0.016%

    No Known Activations